Combining outputs from multiple machine translation systems

TitleCombining outputs from multiple machine translation systems
Publication TypeJournal Articles
Year of Publication2007
AuthorsRosti AVI, Ayan NF, Xiang B, Matsoukas S, Schwartz R, Dorr BJ
JournalHuman Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference
Pagination228 - 235
Date Published2007///

Currently there are several approaches tomachine translation (MT) based on differ-
ent paradigms; e.g., phrasal, hierarchical
and syntax-based. These three approaches
yield similar translation accuracy despite
using fairly different levels of linguistic
knowledge. The availability of such a
variety of systems has led to a growing
interest toward finding better translations
by combining outputs from multiple sys-
tems. This paper describes three differ-
ent approaches to MT system combina-
tion. These combination methods oper-
ate on sentence, phrase and word level
exploiting information from N -best lists,
system scores and target-to-source phrase
alignments. The word-level combination
provides the most robust gains but the
best results on the development test sets
(NIST MT05 and the newsgroup portion
of GALE 2006 dry-run) were achieved by
combining all three methods.